Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1714
    Prev
    Next
    INDEX
    Explanations

    words related to the spread or distribution of information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the distribution and transmission of information or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.75
    lig
    -0.75
     quo
    -0.70
    req
    -0.66
    osher
    -0.66
     Templ
    -0.66
    leans
    -0.65
    chest
    -0.65
    strap
    -0.62
    deen
    -0.62
    POSITIVE LOGITS
     dissemination
    1.13
    sheets
    0.97
     dissemin
    0.97
    atform
    0.89
     disinformation
    0.87
     misinformation
    0.82
     awareness
    0.81
     flyers
    0.80
     leaflets
    0.80
    pread
    0.79
    Activations Density 0.047%

    No Known Activations